In this paper statistical techniques are used to analyze housing submarkets in Sydney and Melbourne, Australia. First, principal component analysis is used to extract a set of factors from the original variables for both local government (LGA) data and combined set of LGA and individual dwelling data. Second, cluster analysis is used on the principal components to determine the most appropriate composition of housing submarkets. Third, hedonic price equations are estimated for each city as a whole, for a priori classifications of submarkets, and for submarkets defined by the cluster analysis. The weighted mean squared errors from the hedonic equations are compared to determine the most appropriate classification of submarkets. In Melbourne, the classification derived form k-means clustering procedure on the dwelling data is significantly better than all other methods of constructing housing submarkets. In some other cases, the statistical analysis produces submarkets which are better, but the improvement is not significantly different from the a priori classifcation